© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 16448
    Prev
    Next
    INDEX
    Explanations

    words related to chanting

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of "chant" and related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    relations
    -0.67
    PF
    -0.67
     Tycoon
    -0.67
     fledgling
    -0.64
    ulent
    -0.64
    drivers
    -0.64
    RW
    -0.63
    ALE
    -0.63
    ettlement
    -0.63
    AMA
    -0.63
    POSITIVE LOGITS
     chanting
    1.43
     chanted
    1.38
     chants
    1.36
     chant
    1.34
     aloud
    0.92
     louder
    0.81
     sung
    0.79
     loudly
    0.78
    hovah
    0.78
     cheering
    0.77
    Activations Density 0.007%

    No Known Activations